Mine water inrush source identification method based on EEMD-Isomap algorithm

Abstract

The invention provides a mine water inrush source identification method based on an EEMD-Isomap algorithm, and belongs to the field of coal mine safety. Comprising the following steps: acquiring Raman spectrum information of mine water; performing noise reduction processing on the Raman spectrum signal; dividing the Raman spectrum signals into a training set and a prediction set; dimensionality reduction processing is carried out on a training set and a prediction set; taking the training set as the input of a kernel K-nearest neighbor algorithm, and establishing a water inrush source identification model; inputting the prediction set into a water inrush source identification model to obtain a prediction result; comparing a prediction result with an actual result in the model to obtain recognition accuracy; and identifying the mine water inrush type by taking the identification accuracy and the identification time as evaluation indexes of the water inrush source type. According to the method provided by the invention, the type of the water inrush source can be intelligently identified, and the method has a great reference value for effectively preventing and controlling water in advance so as to prevent and reduce the occurrence of water disasters.

Description

technical field [0001] The invention belongs to the field of coal mine safety, and in particular relates to a mine water inrush water source identification method based on the EEMD-Isomap algorithm. Background technique [0002] With the complexity of hydrogeological conditions and the increase of mining depth over the years, mine water inrush has become the second largest production problem after coal mine gas. Mine water damage is a disaster that seriously threatens the safety of production and construction in mining areas. Compared with other major accidents and ordinary accidents, major flood accidents have the characteristics of difficulty in rescue and post-disaster production recovery. Once it happens, it will cause more serious casualties and economic losses, and will also bring serious adverse effects to society. The premise of solving the problem of mine water inrush is to identify the type of water inrush, and effectively prevent and control water in advance, so...

AI Technical Summary

Problems solved by technology

[0003] The traditional water chemistry method is used to identify the type of mine water source, which takes a long time and has low analysis and identification efficiency, which cannot meet the real-time requirements for the identification of mine water source type. Other conventional detection methods may damage the sample and cannot achieve non-destructive identification. And requires professionals to operate, time-consuming and labor-intensive

Conventional artificial intelligence algorithms mostly establish prediction models for all bands of spectral data and fail to take into account the impact of redundant information on experimental results and the interrelationships between features. Useless interference noise signals in the data will seriously affect In the recognition results, a large amount of high-dimensional spectral data information makes the recognition model too complex, the analysis efficiency is low, and the recognition accuracy is low, which is not conducive to researchers understanding the process of data generation

Images